Power equipment safety assessment system and method based on big data analysis

Abstract

The present invention discloses a power equipment safety assessment system and method using big data analysis, belonging to the technical field of safety assessment. The system comprises a data acquisition module, a data integration and standardization module, a data storage and quality monitoring module and an intelligent risk assessment module; the data acquisition module is responsible for collecting vibration data of the power equipment to be assessed and its external environment data from different positions; the data integration and standardization module is responsible for integrating the noise, vibration, temperature, and humidity data from different positions and different sensors into one data set, and performing compensation processing; the data storage and quality monitoring module is responsible for storing the integrated data, marking abnormal data, and triggering an alarm mechanism; the intelligent risk assessment module is responsible for performing a comprehensive analysis on the integrated data, assigning a dynamic safety score to each power equipment, and preventing potential equipment accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of safety assessment, and in particular to a system and method for safety assessment of electric power equipment using big data analysis. Background Art

[0002] Power equipment is a key component used for power generation, transmission, distribution and control of power systems, including generators, transformers, transmission lines, switchgear, etc. These devices constitute a complex power system, and through collaborative work, they realize the entire process from power generation to distribution. Power equipment plays a vital role in modern society, providing a stable and reliable power supply for all walks of life. The design and operation of power equipment covers multiple fields such as power engineering, electrical engineering and mechanical engineering, providing indispensable support for the economy and life of society.

[0003] Traditional power equipment safety assessments basically do not consider the impact of external factors on the equipment status. Safety assessments are mainly conducted based on the status of the power equipment. The analysis results are only related to internal components and cannot promptly reflect the impact of changes in the measuring point environment on the equipment safety status. In addition, existing methods often only collect data at a single point, resulting in low assessment accuracy.

[0004] Therefore, the current power equipment safety assessment requires a more advanced and integrated system to solve these problems, and the power equipment safety assessment system and method using big data analysis of the present invention aims to provide a new and more efficient solution. Summary of the invention

[0005] The purpose of the present invention is to provide a power equipment safety assessment system and method using big data analysis to solve the problems raised in the above-mentioned background technology.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a power equipment safety assessment system using big data analysis, including a data acquisition module, a data integration and compensation module, a data storage and quality monitoring module and an intelligent risk assessment module;

[0007] The data acquisition module is the starting point of the system. It is responsible for acquiring real-time data at different locations of the equipment to be evaluated by deploying multiple types of sensors, including vibration sensors, temperature sensors, humidity sensors, etc. Vibration sensors record equipment vibrations, temperature and humidity sensors monitor environmental conditions, and external environmental data include factors such as air temperature and humidity. These sensors work together to achieve comprehensive collection of multi-dimensional information about power equipment and its surrounding environment;

[0008] The data integration and compensation module receives multi-source data from different locations and different sensors, and performs the key tasks of data integration and compensation. During the integration process, different data types and acquisition frequencies are considered to ensure the consistency of data after fusion. The compensation process performs appropriate compensation for different data types, such as vibration, noise, temperature and humidity, to eliminate the differences between sensors and ensure the accuracy and comparability of the integrated data;

[0009] The data storage and quality monitoring module is responsible for storing the integrated and processed data securely and performing quality monitoring during the storage process. This module uses big data storage technology to ensure the scalability and long-term preservation of data. By monitoring the quality of data in real time, marking abnormal data and recording abnormal events, and triggering an alarm mechanism to respond to potential problems in a timely manner, a high level of data quality is guaranteed;

[0010] The intelligent risk assessment module is the core of the system. It gives each power equipment a dynamic safety score by comprehensively analyzing the integrated data. This module not only relies on traditional statistical models, but also combines machine learning and artificial intelligence technologies to more accurately identify potential power equipment accidents. The dynamic score takes into account the changing trends of real-time data and responds sensitively to abnormal situations, thereby achieving timely and accurate monitoring of equipment safety;

[0011] The data acquisition module includes a sensor unit, a vibration data acquisition unit and an environmental data acquisition unit;

[0012] The sensor unit includes the deployment of noise sensors, vibration sensors, temperature sensors and humidity sensors; the vibration data acquisition unit is responsible for collecting vibration data of power equipment from sensors at different positions; the environmental data acquisition unit is responsible for collecting noise data, temperature data and humidity data of the external environment from sensors at different positions.

[0013] The data integration and compensation module includes a data integration unit and a data compensation unit;

[0014] The data integration unit is responsible for integrating the vibration, noise, temperature, and humidity data from different locations and different sensors into a unified power equipment data set; the data compensation unit is responsible for compensating the noise, temperature and humidity data and weighting them with the vibration data to obtain a new data value.

[0015] The data storage and quality monitoring module includes a data storage unit and a data quality monitoring unit;

[0016] The data storage unit is responsible for storing the integrated and compensated data; the data quality monitoring unit is responsible for marking and processing abnormal data, and triggering an alarm mechanism accordingly when the monitoring data exceeds a predetermined threshold.

[0017] The intelligent risk assessment module includes a risk assessment unit and a maintenance plan generation unit;

[0018] The risk assessment unit is responsible for conducting a comprehensive analysis of the integrated data and assigning a dynamic safety score to each power equipment; the maintenance plan generation unit generates a corresponding maintenance plan based on the safety score of the equipment.

[0019] A method for evaluating the safety of electric power equipment using big data analysis, the method comprising the following steps:

[0020] S1. Collect vibration data at different locations of the power equipment to be evaluated and its external environment data;

[0021] S2, integrate and compensate data from different sensors;

[0022] S3, stores the integrated and compensated data and marks the abnormal data;

[0023] S4. Assign a dynamic safety score to the power equipment to be evaluated based on the compensated data to monitor potential power equipment accidents.

[0024] In step S1, the vibration data and external environment data of the power equipment to be evaluated at different locations are collected, and the collection method adopts different time intervals according to different types of data:

[0025] For noise data, which has a high frequency of change, the collection time interval is set to milliseconds; for vibration data, which has a moderate frequency of change, the collection time interval is set to seconds; for temperature and humidity data, which has a low frequency of change, the collection time interval is set to minutes.

[0026] In step S2, the data from different sensors are integrated and compensated using the following technical solutions:

[0027] First, the noise data set of different sensor outputs is obtained as {a1, a2, …, a n}, the vibration data set obtained from different sensors is {b1, b2, …, b n}, the temperature data set obtained from different sensors is {c1,c2,…,c n}, and the humidity data set obtained from different sensors is {d1, d2, …, d n};

[0028] Where a1 is the first noise data obtained, a n is the nth noise data obtained; b1 is the first vibration data obtained, b n is the nth vibration data obtained; c1 is the first temperature data obtained, c n is the nth temperature data obtained; d1 is the first humidity data obtained, d n is the nth humidity data obtained, where n is the number of sensors;

[0029] Then, set the standard value S1 of noise, calculate the first difference between each noise data and the standard value of noise; set the standard value S2 of temperature, calculate the first difference between each temperature data and the standard value of temperature; set the standard value S3 of humidity, calculate the first difference between each humidity data and the standard value of humidity; set the noise alarm value B1, calculate the second difference between each noise data and the noise alarm value; set the alarm value B2 of temperature, calculate the second difference between each temperature data and the temperature alarm value; set the alarm value B3 of humidity, calculate the second difference between each humidity data and the humidity alarm value; compare the first difference with the second difference of different data to obtain standardized data, average the standardized noise data to obtain the noise compensation value p, average the standardized temperature data to obtain the temperature compensation value u, and average the standardized humidity data to obtain the humidity compensation value v. The calculation formulas of p, u and v are as follows:

[0030]

[0031] Among them, a i is the i-th noise data obtained, b i is the i-th vibration data obtained, c i is the obtained temperature data, d i is the i-th humidity data obtained;

[0032] Finally, the weighted average of the compensated environmental data and vibration data is used to obtain the comprehensive index W of different sensor outputs. i :

[0033] W i =α*b i +(1-α)*(p+u+v);

[0034] Among them, α is a weight parameter, which is used to balance the contribution of vibration data and external environment data to the safety assessment of power equipment.

[0035] In step S3, the integrated and compensated data is stored, and a comprehensive index threshold τ is pre-set. If the comprehensive index W i >τ, then mark the data point as abnormal; if the comprehensive index Wi ≤τ, then the data point does not need to be marked.

[0036] In step S4, the compensated data is used as input to output the safety score X corresponding to each sensor position on the power equipment to be evaluated. i The following calculation method is used:

[0037] Assume that the sensor comprehensive index set of the power equipment to be evaluated after data integration and compensation is {W1, W2, ..., W n}, and define the weight data set corresponding to the sensor comprehensive index set as {σ1, σ2, …, σ n}, and σ1+σ2+…+σ n =1;

[0038] X i =W i *σ i ;

[0039] Among them, σ i represents the weight of different sensor outputs in the safety assessment process, i = 1, 2, ..., n;

[0040] The weight set is dynamically adjusted to reflect the impact of each sensor on the safety assessment of power equipment. If it is detected that the sensor data behaves abnormally when a power equipment failure occurs, the weight of the sensor is reduced, and sensor locations with low safety scores on the power equipment are preferentially detected to monitor potential power equipment accidents.

[0041] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0042] 1. By deploying sensors to collect multi-source data, including vibration, noise, temperature and humidity, comprehensive collection of multi-faceted information on power equipment is achieved. Compared with traditional single sensors or data sources, such comprehensive data collection is more comprehensive and more helpful for comprehensive evaluation of equipment status;

[0043] 2. The data integration and compensation module integrates data from different locations and sensors into a unified data set and performs compensation processing. This intelligent integration and compensation can more accurately reflect the true status of power equipment, overcoming the limitations of relying on a single sensor or simple data integration;

[0044] 3. The data storage and quality monitoring module is not only responsible for storing the integrated and processed data, but also for marking and processing abnormal data and triggering the alarm mechanism. Compared with the traditional data storage system, this module is more intelligent in terms of quality monitoring, can identify and handle abnormal situations in a timely manner, and improve the reliability and accuracy of the data;

[0045] 4. The intelligent risk assessment module gives each power equipment a dynamic safety score through comprehensive analysis of the integrated data, and monitors potential power equipment accidents. This intelligent assessment not only relies on traditional static models, but also combines real-time multi-source data, improves the sensitivity to changes in equipment status, and makes the assessment more accurate and real-time. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0047] Figure 1 It is a schematic diagram of the module composition of the power equipment safety assessment system using big data analysis of the present invention;

[0048] Figure 2 It is a schematic flow chart of the steps of the method for safety assessment of electric power equipment using big data analysis according to the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] like Figure 1-2 As shown, the present invention provides the following technical solutions:

[0051] The power equipment safety assessment system using big data analysis includes data acquisition module, data integration and compensation module, data storage and quality monitoring module and intelligent risk assessment module;

[0052] The data acquisition module is the starting point of the system. It is responsible for acquiring real-time data at different locations of the equipment to be evaluated by deploying multiple types of sensors, including vibration sensors, temperature sensors, humidity sensors, etc. Vibration sensors record equipment vibrations, temperature and humidity sensors monitor environmental conditions, and external environmental data include factors such as air temperature and humidity. These sensors work together to achieve comprehensive collection of multi-dimensional information about power equipment and its surrounding environment;

[0053] The data integration and compensation module receives multi-source data from different locations and sensors, and performs the key tasks of data integration and compensation. During the integration process, different data types and acquisition frequencies are considered to ensure the consistency of data after fusion. The compensation processing performs appropriate compensation for different data types, such as vibration, noise, temperature and humidity, to eliminate the differences between sensors and ensure the accuracy and comparability of the integrated data;

[0054] The data storage and quality monitoring module is responsible for storing the integrated and processed data securely and performing quality monitoring during the storage process. This module uses big data storage technology to ensure the scalability and long-term preservation of data. By monitoring the quality of data in real time, marking abnormal data and recording abnormal events, and triggering an alarm mechanism to respond to potential problems in a timely manner, the high level of data quality is guaranteed;

[0055] The intelligent risk assessment module is the core of the system. It gives each power equipment a dynamic safety score by comprehensively analyzing the integrated data. This module not only relies on traditional statistical models, but also combines machine learning and artificial intelligence technologies to more accurately identify potential power equipment accidents. The dynamic score takes into account the changing trends of real-time data and responds sensitively to abnormal situations, thereby achieving timely and accurate monitoring of equipment safety;

[0056] The data acquisition module includes a sensor unit, a vibration data acquisition unit and an environmental data acquisition unit;

[0057] The sensor unit includes the deployment of noise sensors, vibration sensors, temperature sensors and humidity sensors; the vibration data acquisition unit is responsible for collecting vibration data of power equipment from sensors at different locations; the environmental data acquisition unit is responsible for collecting noise data, temperature data and humidity data of the external environment from sensors at different locations.

[0058] The data integration and compensation module includes a data integration unit and a data compensation unit;

[0059] The data integration unit is responsible for integrating the vibration, noise, temperature, and humidity data from different locations and different sensors into a unified power equipment data set; the data compensation unit is responsible for compensating the noise, temperature and humidity data and weighting them with the vibration data to obtain new data values.

[0060] The data storage and quality monitoring module includes a data storage unit and a data quality monitoring unit;

[0061] The data storage unit is responsible for storing the integrated and compensated data; the data quality monitoring unit is responsible for marking and processing abnormal data, and triggering the corresponding alarm mechanism when the monitoring data exceeds the predetermined threshold.

[0062] The intelligent risk assessment module includes a risk assessment unit and a maintenance plan generation unit;

[0063] The risk assessment unit is responsible for conducting a comprehensive analysis of the integrated data and assigning a dynamic safety score to each power equipment; the maintenance plan generation unit generates a corresponding maintenance plan based on the safety score of the equipment.

[0064] The power equipment safety assessment method using big data analysis includes the following steps:

[0065] S1. Collect vibration data at different locations of the power equipment to be evaluated and its external environment data;

[0066] S2, integrate and compensate data from different sensors;

[0067] S3, stores the integrated and compensated data and marks the abnormal data;

[0068] S4. Assign a dynamic safety score to the power equipment to be evaluated based on the compensated data to monitor potential power equipment accidents.

[0069] In step S1, vibration data and external environment data at different locations of the power equipment to be evaluated are collected, and the collection method adopts different time intervals according to different types of data:

[0070] For noise data, which has a high frequency of change, the collection time interval is set to milliseconds; for vibration data, which has a moderate frequency of change, the collection time interval is set to seconds; for temperature and humidity data, which has a low frequency of change, the collection time interval is set to minutes.

[0071] In step S2, the data from different sensors are integrated and compensated using the following technical solutions:

[0072] First, the noise data set of different sensor outputs is obtained as {a1, a2, …, a n}, the vibration data set obtained from different sensors is {b1, b2, …, b n}, the temperature data set obtained from different sensors is {c1,c2,…,c n}, and the humidity data set obtained from different sensors is {d1, d2, …, d n};

[0073] Where a1 is the first noise data obtained, a n is the nth noise data obtained; b1 is the first vibration data obtained, b nis the nth vibration data obtained; c1 is the first temperature data obtained, c n is the nth temperature data obtained; d1 is the first humidity data obtained, d n is the nth humidity data obtained, where n is the number of sensors;

[0074] Then, set the standard value S1 of noise, calculate the first difference between each noise data and the standard value of noise; set the standard value S2 of temperature, calculate the first difference between each temperature data and the standard value of temperature; set the standard value S3 of humidity, calculate the first difference between each humidity data and the standard value of humidity; set the noise alarm value B1, calculate the second difference between each noise data and the noise alarm value; set the alarm value B2 of temperature, calculate the second difference between each temperature data and the temperature alarm value; set the alarm value B3 of humidity, calculate the second difference between each humidity data and the humidity alarm value; compare the first difference with the second difference of different data to obtain standardized data, average the standardized noise data to obtain the noise compensation value p, average the standardized temperature data to obtain the temperature compensation value u, and average the standardized humidity data to obtain the humidity compensation value v. The calculation formulas of p, u and v are as follows:

[0075]

[0076] Among them, a i is the i-th noise data obtained, b i is the i-th vibration data obtained, c i is the obtained temperature data, d i is the i-th humidity data obtained;

[0077] Finally, the weighted average of the compensated environmental data and vibration data is used to obtain the comprehensive index W of different sensor outputs. i :

[0078] W i =α*b i +(1-α)*(p+u+v);

[0079] Among them, α is a weight parameter, which is used to balance the contribution of vibration data and external environment data to the safety assessment of power equipment.

[0080] In step S3, the integrated and compensated data is stored, and a comprehensive index threshold τ is pre-set. If the comprehensive index W i >τ, then mark the data point as abnormal; if the comprehensive index W i ≤τ, then the data point does not need to be marked.

[0081] In step S4, the compensated data is used as input to output the safety score X corresponding to each sensor position on the power equipment to be evaluated. i The following calculation method is used:

[0082] Assume that the sensor comprehensive index set of the power equipment to be evaluated after data integration and compensation is {W1, W2, ..., W n}, and define the weight data set corresponding to the sensor comprehensive index set as {σ1, σ2, …, σ n}, and σ1+σ2+…+σ n =1;

[0083] X i =W i *σ i ;

[0084] Among them, σ i represents the weight of different sensor outputs in the safety assessment process, i = 1, 2, ..., n;

[0085] The weight set is dynamically adjusted to reflect the impact of each sensor on the safety assessment of power equipment. If it is detected that the sensor data behaves abnormally when a power equipment failure occurs, the weight of the sensor is reduced, and sensor locations with low safety scores on the power equipment are preferentially detected to monitor potential power equipment accidents.

[0086] Embodiment 1:

[0087] The noise data obtained from the noise sensors at different positions at millisecond time intervals are {70, 75, 80}, the vibration data obtained from the vibration sensors at different positions at second time intervals are {0.5, 0.6, 0.7}, the temperature data obtained from the temperature sensors at different positions at minute time intervals are {25, 26, 27}, and the humidity data obtained from the humidity sensors at different positions at minute time intervals are {30, 35, 40}.

[0088] Then, set the standard value of noise S1=75, calculate the first difference between each noise data and the standard value of noise; set the standard value of temperature S2=26, calculate the first difference between each temperature data and the standard value of temperature; set the standard value of humidity S3=35, calculate the first difference between each humidity data and the standard value of humidity: set the noise alarm value B1=85, calculate the second difference between each noise data and the noise alarm value; set the alarm value of temperature B2=30, calculate the second difference between each temperature data and the temperature alarm value; set the alarm value of humidity B3=45, calculate the second difference between each humidity data and the humidity alarm value; compare the first difference with the second difference of different data to obtain standardized data, average the standardized noise data of different data to obtain the noise compensation value p, average the standardized temperature data of each position to obtain the temperature compensation value u, and average the standardized humidity data of each position to obtain the humidity compensation value v. The calculation formulas of p, u and v are as follows:

[0089]

[0090]

[0091]

[0092] Assume the weight parameter α = 0.5, and take the weighted average of the compensated environmental data and vibration data to obtain the comprehensive index W of different sensor outputs. i :

[0093] W1=α*b1+(1-α)*(p+u+v)=0.783;

[0094] W2=α*b2+(1-α)*(p+u+v)=0.833;

[0095] W3=α*b3+(1-α)*(p+u+v)=0.833;

[0096] The compensated data {0.783, 0.833, 0.833} is used as input to output the safety score X corresponding to each sensor position of the power equipment to be evaluated. i The following calculation method is used:

[0097] Assume that the sensor output data set of the power equipment to be evaluated after data integration compensation is {0.783, 0.833, 0.833}, and define the weight data set of the sensor output data as {0.3, 0.5, 0.2};

[0098] X1=W1*σ1=0.235; X2=W2*σ2=0.417; X3=W3*σ3=0.167;

[0099] Then, the weight set is dynamically adjusted. For example, if the data detected at a certain sensor location of the power equipment is associated with a power equipment failure, the weight of the sensor is reduced, such as reducing σ1 from 0.3 to 0.2; then, the safety score at each power equipment location is recalculated, and sensor locations with low safety scores on the power equipment are detected first, thereby monitoring potential power equipment accidents.

[0100] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0101] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The power equipment safety assessment system using big data analysis is characterized by: It includes data acquisition module, data integration and compensation module, data storage and quality monitoring module and intelligent risk assessment module; The data acquisition module is responsible for collecting vibration data and external environment data at different locations of the power equipment to be evaluated by deploying sensors; the data integration and compensation module is responsible for integrating vibration, noise, temperature and humidity data from different locations and different sensors into one data set and performing compensation processing; the data storage and quality monitoring module is responsible for storing the integrated data, marking and processing abnormal data, and triggering an alarm mechanism; the intelligent risk assessment module is responsible for comprehensive analysis of the integrated data, assigning a dynamic safety score to each power equipment, and monitoring potential power equipment accidents; Wherein, the data integration and compensation module includes a data integration unit and a data compensation unit; The data integration unit is responsible for integrating the vibration, noise, temperature, and humidity data from different locations and different sensors into a unified data set of power equipment; the data compensation unit is responsible for compensating the noise, temperature, and humidity data and weighting them with the vibration data to obtain a new data value; The data integration unit and the data compensation unit integrate and compensate the data from different sensors using the following technical solutions: First, the noise data set of different sensor outputs is obtained as {a1, a2, …, a n }, the vibration data set obtained from different sensors is {b1, b2, …, b n }, the temperature data set obtained from different sensors is {c1,c2,…,c n }, and the humidity data set obtained from different sensors is {d1, d2, …, d n }; Where a1 is the first noise data obtained, a n is the nth noise data obtained; b1 is the first vibration data obtained, b n is the nth vibration data obtained; c1 is the first temperature data obtained, c n is the nth temperature data obtained; d1 is the first humidity data obtained, d n is the nth humidity data obtained, where n is the number of deployed sensors; Then, set the standard value S1 of noise, calculate the first difference between each noise data and the standard value of noise; set the standard value S2 of temperature, calculate the first difference between each temperature data and the standard value of temperature; set the standard value S3 of humidity, calculate the first difference between each humidity data and the standard value of humidity; set the noise alarm value B1, calculate the second difference between each noise data and the noise alarm value; set the alarm value B2 of temperature, calculate the second difference between each temperature data and the temperature alarm value; set the alarm value B3 of humidity, calculate the second difference between each humidity data and the humidity alarm value; compare the first difference with the second difference of different data to obtain standardized data, average the standardized noise data to obtain the noise compensation value p, average the standardized temperature data to obtain the temperature compensation value u, and average the standardized humidity data to obtain the humidity compensation value v. The calculation formulas of p, u and v are as follows: Among them, a i is the i-th noise data obtained, b i is the i-th vibration data obtained, c i is the obtained temperature data, d i is the i-th humidity data obtained; Finally, the compensated environmental data and vibration data are weighted averaged to obtain the comprehensive index W of different sensor outputs. i : W i =a*b i +(1-a)*(p+u+v); Among them, α is a weight parameter, which is used to balance the contribution of vibration data and external environment data to the safety assessment of power equipment.

2. The power equipment safety assessment system using big data analysis according to claim 1 is characterized in that: The data acquisition module includes a sensor unit, a vibration data acquisition unit and an environmental data acquisition unit; The sensor unit includes the deployment of noise sensors, vibration sensors, temperature sensors and humidity sensors; the vibration data acquisition unit is responsible for collecting vibration data of power equipment from sensors at different positions; the environmental data acquisition unit is responsible for collecting noise data, temperature data and humidity data of the external environment from sensors at different positions.

3. The power equipment safety assessment system using big data analysis according to claim 1 is characterized in that: The data storage and quality monitoring module includes a data storage unit and a data quality monitoring unit; The data storage unit is responsible for storing the integrated and compensated data; the data quality monitoring unit is responsible for marking and processing abnormal data, and triggering a corresponding alarm mechanism when it is found that the monitoring data exceeds a predetermined threshold.

4. The power equipment safety assessment system using big data analysis according to claim 1 is characterized in that: The intelligent risk assessment module includes a risk assessment unit and a maintenance plan generation unit; The risk assessment unit is responsible for conducting a comprehensive analysis of the integrated data and assigning a dynamic safety score to each power device; The maintenance plan generating unit generates a corresponding maintenance plan according to the safety score of the equipment.

5. A method for evaluating the safety of electric equipment using big data analysis using the electric equipment safety evaluation system using big data analysis according to any one of claims 1 to 4, characterized in that: The power equipment safety assessment method comprises the following steps: S1. Collect vibration data at different locations of the power equipment to be evaluated and its external environment data; S2, integrate and compensate data from different sensors; S3, stores the integrated and compensated data and marks abnormal data; S4. Assign a dynamic safety score to the power equipment to be evaluated based on the compensated data to monitor potential power equipment accidents.

6. The method for safety assessment of electric power equipment using big data analysis according to claim 5 is characterized in that: In step S1, the vibration data and external environment data of the power equipment to be evaluated at different locations are collected, and the collection method adopts different time intervals according to different types of data: For noise data, the collection time interval is set to milliseconds; for vibration data, the collection time interval is set to seconds; for temperature and humidity data, the collection time interval is set to minutes.

7. The method for safety assessment of electric power equipment using big data analysis according to claim 5 is characterized in that: In step S3, the integrated and compensated data is stored, and a comprehensive index threshold τ is pre-set. If the comprehensive index W i >τ, then mark the data point as abnormal; if the comprehensive index W i ≤τ, then the data point does not need to be marked.

8. The method for safety assessment of electric power equipment using big data analysis according to claim 5 is characterized in that: In step S4, the compensated data is used as input to output the safety score X of each sensor location on the power equipment to be evaluated. i The following calculation method is used: Assume that the comprehensive index set of different sensor outputs of the power equipment to be evaluated after data integration and compensation is {W1, W2, ..., W n }, and define the weight data set corresponding to the comprehensive index set output by the sensor as {σ1, σ2, …, σ n }, and σ1+σ2+…+σ n =1; X i =W i *s i ; Among them, σ i represents the weight of different sensor outputs in the safety assessment process, i = 1, 2, ..., n; The weight set is dynamically adjusted to reflect the impact of each sensor on the safety assessment of power equipment. If it is detected that the sensor data behaves abnormally when a power equipment failure occurs, the weight of the sensor is reduced, and sensor locations with low safety scores on the power equipment are detected first.

Images